Project

sealedrose

0.0
The project is in a healthy, maintained state
Sealed Rose client library for analyzing video and images for synthetic media, deepfakes, face swaps, and diffusion artifacts.
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
 Dependencies

Runtime

 Project Readme

Sealed Rose SDK & DFIR Media Forensics Tools

License: MIT npm version PyPI version Docker Pulls OpenSSF Best Practices

Official open-source developer SDKs and Digital Forensics & Incident Response (DFIR) tools for Sealed Rose — AI Deepfake Detection, Synthetic Media Analysis, and Frame-Level Forensics.

Built for DFIR analysts, SOC teams, threat intelligence researchers, and incident response pipelines investigating:

  • Executive & Employee Impersonation (synthetic video/audio in business communications)
  • Identity & KYC Fraud (face swap manipulations in onboarding videos)
  • Social Engineering & Phishing (generative media campaigns)
  • Digital Evidence Verification (frame-by-frame anomaly detection and model attribution)

Interactive Triage Engine (No Code)

DFIR teams can instantly triage suspicious media files without an account or API setup using the free web verification engine: 👉 Sealed Rose Deepfake Video & Image Detector


SDKs & Packages

Language / Tool Package / Image Documentation
JavaScript / TypeScript npm install sealedrose npm Package · SDK README
Python pip install sealedrose PyPI Package · Python README
PHP composer require sealedrose/sealedrose-sdk Packagist Package · PHP README
Ruby gem install sealedrose RubyGems Package · Ruby README
Docker docker pull derekgallardo01/sealed-rose-detector Docker Hub · Docker README
VS Code Extension Sealed Rose Media Detector Visual Studio Marketplace

Quick Starts

1. Python SDK

Ideal for incident response scripts, Jupyter forensic notebooks, and automated IR triaging pipelines:

pip install sealedrose
from sealedrose import SealedRose

client = SealedRose()

# Triage a suspicious video file collected during an incident
result = client.verify_video(file_path="evidence/suspicious_exec_call.mp4")

print(f"Verdict: {result.get('verdict')}")           # e.g., "AI Deepfake Detected"
print(f"Confidence Score: {result.get('deepfakeScore')}") # 0.0 to 1.0
print(f"Forensic Indicators: {result.get('indicators')}")

2. Node.js / TypeScript SDK

npm install sealedrose
import { SealedRose } from 'sealedrose';

const client = new SealedRose();

// Verify video authenticity via public URL or local stream
const result = await client.verifyVideo({
  url: 'https://incident-evidence.internal/case-2026-092/payload.mp4'
});

console.log(result.verdict);       // "Looks Real" or "AI Deepfake Detected"
console.log(result.deepfakeScore); // Confidence rating

3. Docker Container

For air-gapped sandboxes or containerized security pipelines:

docker run -it --rm derekgallardo01/sealed-rose-detector:latest

Incident Response & Forensic Capabilities

  • Frame-Level Artifact Detection: Analyzes compression discrepancies, optical flow discontinuities, facial landmark micro-jitters, and frequency-domain anomalies.
  • Generative AI Attribution: Identifies artifacts characteristic of diffusion engines (Midjourney, Stable Diffusion, Flux, Sora, Runway Gen-3, Kling, Google Veo).
  • Fast Triaging API: Designed to plug directly into SOAR workflows, SIEM alerting hooks, and ticketing pipelines.

Free Resources & Browser Tools


License

This project and its SDKs are licensed under the MIT License — see the LICENSE file for details.